mobilebert_sa_GLUE_Experiment_qnli
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6487
- Accuracy: 0.6094
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6754 | 1.0 | 819 | 0.6491 | 0.6178 |
| 0.6369 | 2.0 | 1638 | 0.6487 | 0.6094 |
| 0.6125 | 3.0 | 2457 | 0.6555 | 0.6088 |
| 0.5942 | 4.0 | 3276 | 0.6647 | 0.6028 |
| 0.5805 | 5.0 | 4095 | 0.6735 | 0.5934 |
| 0.5689 | 6.0 | 4914 | 0.6893 | 0.5978 |
| 0.5587 | 7.0 | 5733 | 0.7055 | 0.5896 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2